Ghost is a publishing platform for creating websites, blogs, memberships, subscriptions, and newsletters. Publishers and developers can use it through managed hosting or run it themselves, while contributors work on its monorepo, themes, and API.
Borrowing it
Nothing to install: this file belongs to TryGhost/Ghost. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/TryGhost/Ghost/main/.agents/skills/shade-new-component/SKILL.mdgit clone --depth 1 https://github.com/TryGhost/GhostWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/skills/tryghost/ghost/shade-new-component)<a href="https://agentmods.dev/skills/tryghost/ghost/shade-new-component"><img src="https://agentmods.dev/badge/skills/tryghost/ghost/shade-new-component/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/tryghost/ghost/shade-new-component"><img src="https://agentmods.dev/badge/skills/tryghost/ghost/shade-new-component.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00047 | $0.01297 |
| Opus 5.5 | $0.00019 | $0.00519 |
| Sonnet 5.5 | $0.00009 | $0.00259 |
| Haiku 4.5 | $0.00005 | $0.00130 |
Grade A, and why
Shade new component scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 2d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 129 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Shade — new component / pattern checklist
Before marking a Shade component or pattern done, this checklist must pass.
Files and naming
- File: kebab-case (
dropdown-menu.tsx) — matches ShadCN CLI output. Don't rename for casing. - Exported identifier: PascalCase (
DropdownMenu). - Hooks, functions, variables: camelCase.
- Sibling
<name>.stories.tsxis required (same folder). - A component file exports only components and types, so Fast Refresh can hot-update it (ESLint enforces this). An exported
cva()config goes in a sibling<name>-variants.ts; exported hooks, contexts and helpers go in their own sibling module (sidebar-context.ts). These siblings belong to the component; they aren't Recipes. - Inside Shade itself, import via the
@/alias (@/lib/utils,@/components/ui/input-surface).
Storybook title prefix
| Layer | Title |
|---|---|
| Primitive | Primitives / <Name> |
| Component | Components / <Name> |
| Recipe | Recipes / <Name> |
| Pattern | Patterns / <Name> |
| Token gallery | Tokens / <Topic> |
Required on every story file:
tags: ['autodocs']parameters.docs.description.component— short one-line summary- Per-story
parameters.docs.description.story— one-liner explaining when to use that variant - One story per important variant/state. Many small focused stories > one prose-heavy story.
Component shape
// thing-variants.ts
import {cva} from 'class-variance-authority';
const thingVariants = cva('base-classes-here', {
variants: {
variant: {default: '...', destructive: '...'},
size: {default: '...', sm: '...'}
},
defaultVariants: {variant: 'default', size: 'default'}
});
export {thingVariants};
// thing.tsx
import * as React from 'react';
import {type VariantProps} from 'class-variance-authority';
import {thingVariants} from '@/components/ui/thing-variants';
import {cn} from '@/lib/utils';
export interface ThingProps
extends React.HTMLAttributes<HTMLDivElement>,
VariantProps<typeof thingVariants> {}
const Thing = React.forwardRef<HTMLDivElement, ThingProps>(
({className, variant, size, ...props}, ref) => (
<div
ref={ref}
className={cn(thingVariants({variant, size, className}))}
{...props}
/>
)
);
Thing.displayName = 'Thing';
export {Thing};
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 2d ago Changed 221fe614abb5
- 18d ago Changed · +11 lines 8e321e3ee129
- 2mo ago First seen · 118 lines · 47 tokens per session scan A da66a256389d
Shade new component is a skill published in the GitHub repository TryGhost/Ghost (55,632 stars, last pushed today), licensed MIT. It adds 47 tokens to every session and 1,297 once invoked, about $0.0002 per session on Opus 5.5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other skills, from other repositories
cms-metadata-tagger
Takes a finished piece of content and produces a complete, archive-ready metadata record — including descriptive tags, subject classifications, rights notes, and an archival summary — for entry into a content management or digital archive system.
cms-metadata-writer
Writes structured metadata fields — title tag, meta description, tags, category, slug, and Open Graph text — for a CMS entry, optimized for search discoverability and social sharing.
cms-fields-writer
Generates the complete set of metadata fields — tags, categories, keywords, slug, and summary — needed to publish a piece of content in a content management system, ready to copy and paste into each field.
author-bio-writer
Writes a concise, publication-ready author bio in the appropriate register and length for the target outlet — from a one-line byline tag to a full contributor page paragraph.
manuscript-formatter
Reformats a manuscript, article, or long-form text to match a specific publication's structural and style requirements — adjusting headings, paragraph spacing, citation format, pull-quote placement, and front matter without altering the content itself.
platform-distribution-advisor
Recommends the best platforms for distributing a finished piece of content, with a ranked list and a brief rationale for each recommendation based on the content type, format, length, and intended audience.